Table 9 Rationale for using ADA and EGOA for Feature Selection.
From: A hybrid deep learning model for detection and mitigation of DDoS attacks in VANETs
Aspect | ADA | EGOA |
|---|---|---|
Swarm behavior | Separation, alignment, cohesion | Nonlinear social interaction + adaptive decay |
Adaptivity | Dynamic inertia and behavior weights | Oscillating step size for fine convergence |
Exploration vs. Exploitation | Balanced via adaptive coefficients | Enhanced local search via cosine decay |
Time complexity | O(Pâ‹…Tâ‹…FlogF) | Same, with fewer iterations due to faster convergence |
Convergence guarantee | Fitness stagnation + MaxIter | Fitness stagnation + adaptive step decay |
